Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4493
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss meaning, interpretations, and references to ideas or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istream
    -0.52
    LookAnd
    -0.52
    mybatisplus
    -0.47
    routeProvider
    -0.45
    drawSprites
    -0.45
    yntaxException
    -0.45
     okaz
    -0.44
    isStatic
    -0.44
    getMenuInflater
    -0.44
    кипедия
    -0.44
    POSITIVE LOGITS
    новниш
    0.63
     Literally
    0.63
    Means
    0.57
    DoubleQuotes
    0.57
     referring
    0.56
     alludes
    0.56
    Literally
    0.56
    yarnpkg
    0.56
     Means
    0.54
    省市镇
    0.53
    Activations Density 0.232%

    No Known Activations